hf06/conplex

Adapting protein language models and contrastive learning for highly-accurate drug-target interaction prediction.

ConPLex

🚧🚧 Please note that ConPLex v0.1.0 is currently a pre-release and is actively being developed. For the code used to generate our PNAS results, see the manuscript code 🚧🚧

• Homepage
• Documentation

Abstract

Sequence-based prediction of drug-target interactions has the potential to accelerate drug discovery by complementing experimental screens. Such computational prediction needs to be generalizable and scalable while remaining sensitive to subtle variations in the inputs. However, current computational techniques fail to simultaneously meet these goals, often sacrificing performance on one to achieve the others. We develop a deep learning model, ConPLex, successfully leveraging the advances in pre-trained protein language models ("PLex") and employing a novel protein-anchored contrastive co-embedding ("Con") to outperform state-of-the-art approaches. ConPLex achieves high accuracy, broad adaptivity to unseen data, and specificity against decoy compounds. It makes predictions of binding based on the distance between learned representations, enabling predictions at the scale of massive compound libraries and the human proteome. Experimental testing of 19 kinase-drug interaction predictions validated 12 interactions, including four with sub-nanomolar affinity, plus a novel strongly-binding EPHB1 inhibitor ($K_D = 1.3nM$). Furthermore, ConPLex embeddings are interpretable, which enables us to visualize the drug-target embedding space and use embeddings to characterize the function of human cell-surface proteins. We anticipate ConPLex will facilitate novel drug discovery by making highly sensitive in-silico drug screening feasible at genome scale.

Installation

Install from PyPI

pip install conplex-dti
conplex-dti --help

Compile from Source

git clone https://github.com/samsledje/ConPLex.git
cd ConPLex
conda create -n conplex-dti python=3.9
conda activate conplex-dti
make poetry-download
export PATH=[poetry install location]:PATH
export PYTHON_KEYRING_BACKEND=keyring.backends.null.Keyring
make install
conplex-dti --help

Usage

Download benchmark data sets

...

Run benchmark training

conplex-dti train --run-id TestRun --config config/default_config.yaml

Make predictions with a trained model

...

Visualize co-embedding space

...

Reference

If you use ConPLex, please cite “Contrastive learning in protein language space predicts interactions between drugs and protein targets” by Rohit Singh*, Samuel Sledzieski*, Bryan Bryson, Lenore Cowen and Bonnie Berger, currently in press at PNAS.

TBD .bibtex citation

Manuscript Code

Code used to generate results in the manuscript can be found in the development repository